Adaptive signal control for bus service reliability with connected vehicle technology via reinforcement learning

Chow, Ahf; Su, Ziyi; Liang, Enming; Zhong, Renxin

doi:10.1016/j.trc.2021.103264

Cited by 27 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The in-vehicle device can present drivers with real-time traffic conditions nearby and traffic images of major roads and automatically recommend the optimal driving plan to improve the efficiency of traffic operation [101,102]. Meanwhile, the position and speed of each vehicle will be uploaded to the cloud synchronously, ensuring the real-time and accuracy of traffic information in the area.…”

Section: Traffic Controlmentioning

confidence: 99%

Trends and Emerging Technologies for the Development of Electric Vehicles

Liu

Lau

et al. 2022

Energies

View full text Add to dashboard Cite

In response to severe environmental and energy crises, the world is increasingly focusing on electric vehicles (EVs) and related emerging technologies. Emerging technologies for EVs have great potential to accelerate the development of smart and sustainable transportation and help build future smart cities. This paper reviews new trends and emerging EV technologies, including wireless charging, smart power distribution, vehicle-to-home (V2H) and vehicle-to-grid (V2G) systems, connected vehicles, and autonomous driving. The opportunities, challenges, and prospects for emerging EV technologies are systematically discussed. The successful commercialization development cases of emerging EV technologies worldwide are provided. This review serves as a reference and guide for future technological development and commercialization of EVs and offers perspectives and recommendations on future smart transportation.

show abstract

Section: Traffic Controlmentioning

confidence: 99%

Trends and Emerging Technologies for the Development of Electric Vehicles

Liu

Lau

et al. 2022

Energies

View full text Add to dashboard Cite

show abstract

“…Moreover, the location regarding the trained feature stored in the data is calculated by the Equation (18).…”

Section: Classification Processmentioning

confidence: 99%

“…The hybrid kinematic traffic system was designed by Chow et al 18 to know the bus service status every time. The proposed model is tested for the London corridor.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A novel optimized intelligent green signal timing system for urban corridor

Malathi

Kumar

2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary In the real world, fixed traffic time signal control is commonly used due to the low implementation cost. However, these signal systems do not achieve the best performance, especially when the unbalanced traffic demand. Hence, a novel buffalo based recurrent fuzzy green timing system (BRFGTS) is proposed to enhance the green timing. Moreover, traffic speed data was initially collected to implement the proposed model. Consequently, after neural layer training, the preprocessing was performed to eliminate the unwanted data. After that, feature extraction is done to take the required features from the preprocessed data. After extracting the features, the data are moved through the classification process. A recurrent network‐based approach trains the data in the classification process. Furthermore, the fitness of buffalo is updated in the classification layer of the recurrent model to reduce the traveling time by improving the shortest route prediction to identify the other path to travel vehicle. The proposed green timing system is implemented in the tool named MATLAB. Subsequently, the results from the proposed model are compared with different techniques. Thus the recorded minimum traveling time by the presented BRFGTS is 20.5 s; compared to other models, it has minimized the traveling time by 40%. Also, the proposed model has minimized the queue length by 38% than the compared models. Hence, the robustness of the novel BRFGTS has been proved.

show abstract

“…Recently, with the rapid development of artificial intelligence, the reinforcement learning (RL) algorithms have attracted the gaze of researchers in both optimal control community and transportation community. Through conducting the learning procedure, an agent can select an optimal action for each observation to maximize its cumulative expected reward (i.e., usually is the optimization goal), and this process can be usually achieved in a realtime fashion (Chow et al, 2021). By leveraging deep neural networks, the integrating outcome, which is known as deep reinforcement learning (DRL), has the ability to approximate the optimal policy in most of the control tasks, even with high-dimension state space .…”

Section: Introductionmentioning

confidence: 99%

Eco-driving for Electric Connected Vehicles at Signalized Intersections: A Parameterized Reinforcement Learning approach

Lü¹,

Zhang²,

Li³

2022

Preprint

View full text Add to dashboard Cite

This paper proposes an eco-driving framework for electric connected vehicles (CVs) based on reinforcement learning (RL) to improve vehicle energy efficiency at signalized intersections. The vehicle agent is specified by integrating the model-based car-following policy, lane-changing policy, and the RL policy, to ensure safe operation of a CV. Subsequently, a Markov Decision Process (MDP) is formulated, which enables the vehicle to perform longitudinal control and lateral decisions, jointly optimizing the car-following and lane-changing behaviors of the CVs in the vicinity of intersections. Then, the hybrid action space is parameterized as a hierarchical structure and thereby trains the agents with two-dimensional motion patterns in a dynamic traffic environment. Finally, our proposed methods are evaluated in SUMO software from both a single-vehicle-based perspective and a flow-based perspective. The results show that our strategy can significantly reduce energy consumption by learning proper action schemes without any interruption of other human-driven vehicles (HDVs).

show abstract

Adaptive signal control for bus service reliability with connected vehicle technology via reinforcement learning

Cited by 27 publications

References 33 publications

Trends and Emerging Technologies for the Development of Electric Vehicles

Trends and Emerging Technologies for the Development of Electric Vehicles

A novel optimized intelligent green signal timing system for urban corridor

Eco-driving for Electric Connected Vehicles at Signalized Intersections: A Parameterized Reinforcement Learning approach

Contact Info

Product

Resources

About